© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90039
    Prev
    Next
    INDEX
    Explanations

    special formatting or structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tach
    -0.08
    ardu
    -0.08
    ardi
    -0.07
    char
    -0.06
    зÑĭ
    -0.06
    हल
    -0.06
    ottle
    -0.06
    olvers
    -0.06
    isy
    -0.06
    dish
    -0.06
    POSITIVE LOGITS
    _mD
    0.06
     Strap
    0.06
    bbe
    0.06
     Recorded
    0.06
    设
    0.05
    /mainwindow
    0.05
    (Customer
    0.05
    oris
    0.05
    orca
    0.05
    eso
    0.05
    Activations Density 0.000%

    No Known Activations